Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/firsttv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urlparse
   6 from ..utils import (
   7     int_or_none,
   8     qualities,
   9     unified_strdate,
  10 )
  11
  12
  13 class FirstTVIE(InfoExtractor):
  14     IE_NAME = '1tv'
  15     IE_DESC = 'Первый канал'
  16     _VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>[^/?#]+)'
  17
  18     _TESTS = [{
  19         # single format
  20         'url': 'http://www.1tv.ru/shows/naedine-so-vsemi/vypuski/gost-lyudmila-senchina-naedine-so-vsemi-vypusk-ot-12-02-2015',
  21         'md5': 'a1b6b60d530ebcf8daacf4565762bbaf',
  22         'info_dict': {
  23             'id': '40049',
  24             'ext': 'mp4',
  25             'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
  26             'description': 'md5:36a39c1d19618fec57d12efe212a8370',
  27             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
  28             'upload_date': '20150212',
  29             'duration': 2694,
  30         },
  31     }, {
  32         # multiple formats
  33         'url': 'http://www.1tv.ru/shows/dobroe-utro/pro-zdorove/vesennyaya-allergiya-dobroe-utro-fragment-vypuska-ot-07042016',
  34         'info_dict': {
  35             'id': '364746',
  36             'ext': 'mp4',
  37             'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016',
  38             'description': 'md5:a242eea0031fd180a4497d52640a9572',
  39             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
  40             'upload_date': '20160407',
  41             'duration': 179,
  42             'formats': 'mincount:3',
  43         },
  44         'params': {
  45             'skip_download': True,
  46         },
  47     }]
  48
  49     def _real_extract(self, url):
  50         display_id = self._match_id(url)
  51
  52         webpage = self._download_webpage(url, display_id)
  53         playlist_url = compat_urlparse.urljoin(url, self._search_regex(
  54             r'data-playlist-url="([^"]+)', webpage, 'playlist url'))
  55
  56         item = self._download_json(playlist_url, display_id)[0]
  57         video_id = item['id']
  58         quality = qualities(('ld', 'sd', 'hd', ))
  59         formats = []
  60         for f in item.get('mbr', []):
  61             src = f.get('src')
  62             if not src:
  63                 continue
  64             fname = f.get('name')
  65             formats.append({
  66                 'url': src,
  67                 'format_id': fname,
  68                 'quality': quality(fname),
  69             })
  70         self._sort_formats(formats)
  71
  72         title = self._html_search_regex(
  73             (r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
  74              r"'title'\s*:\s*'([^']+)'"),
  75             webpage, 'title', default=None) or item['title']
  76         description = self._html_search_regex(
  77             r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
  78             webpage, 'description', default=None) or self._html_search_meta(
  79             'description', webpage, 'description')
  80         duration = int_or_none(self._html_search_meta(
  81             'video:duration', webpage, 'video duration', fatal=False))
  82         upload_date = unified_strdate(self._html_search_meta(
  83             'ya:ovs:upload_date', webpage, 'upload date', fatal=False))
  84
  85         return {
  86             'id': video_id,
  87             'thumbnail': item.get('poster') or self._og_search_thumbnail(webpage),
  88             'title': title,
  89             'description': description,
  90             'upload_date': upload_date,
  91             'duration': int_or_none(duration),
  92             'formats': formats
  93         }